agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v1 1/5] Allow to use multiple shared memory mappings 309+ messages / 2 participants [nested] [flat]
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v1 1/5] Allow to use multiple shared memory mappings @ 2024-10-09 13:41 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory slot. There is only fixed amount of available slots, currently only one main shared memory slot is allocated. A new shared memory API is introduces, extended with a slot as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory slot. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 2 +- src/backend/storage/ipc/ipci.c | 61 ++++++------ src/backend/storage/ipc/shmem.c | 133 ++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 10 ++ 13 files changed, 258 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 64186ec0a7..b97723d2ed 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 5b88a92bc9..8ef95b12c9 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 362a37d3b3..065a5b63ac 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_slot; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping slots */ +static int next_free_slot = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_slot) +{ + switch (shmem_slot) + { + case MAIN_SHMEM_SLOT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_slot; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_slot), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("slot[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_slot)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_slot; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_slot]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_slot = next_free_slot; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_slot++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_slot; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_slot; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index f2b54bdfda..d62084cc0d 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_slot) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index b06e4b8452..2aabd4a77f 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -68,7 +68,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 35fa2e1dda..8224015b53 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_slot) { Size size; int numSemas; @@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int slot = 0; slot < ANON_MAPPINGS; slot++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, slot); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSlot(seghdr, slot); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, slot); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSlot(slot); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -359,7 +362,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 6d5f083986..c670b9cf43 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,17 +75,12 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSlot(Size size, Size *allocated_size, + int shmem_slot); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ - -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ +ShmemSegment Segments[ANON_MAPPINGS]; static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ @@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(void *seghdr) { - PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT); +} - ShmemSegHdr = shmhdr; - ShmemBase = (void *) shmhdr; - ShmemEnd = (char *) ShmemBase + shmhdr->totalsize; +void +InitShmemAccessInSlot(void *seghdr, int shmem_slot) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_slot]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSlot(MAIN_SHMEM_SLOT); +} + +void +InitShmemAllocationInSlot(int shmem_slot) +{ + PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +130,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_slot].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +157,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocInSlot(Size size, int shmem_slot) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +197,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT); +} + +static void * +ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot) { Size newStart; Size newFree; @@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_slot].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize) { - newSpace = (void *) ((char *) ShmemBase + newStart); - ShmemSegHdr->freeoffset = newFree; + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_slot].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT); +} + +void * +ShmemAllocUnlockedInSlot(Size size, int shmem_slot) { Size newStart; Size newFree; @@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_slot].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree; - newSpace = (void *) ((char *) ShmemBase + newStart); + newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart); Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT); +} + +bool +ShmemAddrIsValidInSlot(const void *addr, int shmem_slot) +{ + return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd); } /* @@ -334,6 +365,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SLOT); +} + +HTAB * +ShmemInitHashInSlot(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_slot) /* in which slot to keep the table */ { bool found; void *location; @@ -350,9 +393,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSlot(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_slot); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +428,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT); +} + +void * +ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSlot(size, shmem_slot); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d", + name, shmem_slot))); } if (*foundPtr) @@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index e765754d80..fb0c33bf17 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index f190e6e5e4..aef80e049b 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -23,6 +23,7 @@ #include "storage/latch.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index b2d062781e..be4b131288 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index dfef79ac96..081fffaf16 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_slot); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 3065ff5be7..e968deeef7 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +// Number of available slots for anonymous memory mappings +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main slot, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SLOT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 842989111c..d3e9cc721d 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -28,15 +28,25 @@ /* shmem.c */ extern PGDLLIMPORT slock_t *ShmemLock; extern void InitShmemAccess(void *seghdr); +extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSlot(int shmem_slot); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSlot(Size size, int shmem_slot); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size, + HASHCTL *infoP, int hash_flags, int shmem_slot); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr, + int shmem_slot); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 2488058dc356a43455b21a099ea879fff9266634 -- 2.45.1 --ers4zrhjqnhlajas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v2 1/6] Allow to use multiple shared memory mappings @ 2025-02-19 16:43 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 5 +- src/include/storage/buf_internals.h | 1 + src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 13 files changed, 272 insertions(+), 124 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..843b1b3220f 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + void *shmem; /* Pointer to the start of the mapped memory */ + void *seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index e4d5b944e12..9d526eb43fd 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 174eed70367..4f6c707c204 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -360,7 +365,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index f1e74f184f1..40aa4014b5f 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -81,6 +81,7 @@ #include "pgstat.h" #include "port/pg_bitutils.h" #include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/spin.h" @@ -607,9 +608,9 @@ LWLockNewTrancheId(void) LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h index 1a65342177d..4595f5a9676 100644 --- a/src/include/storage/buf_internals.h +++ b/src/include/storage/buf_internals.h @@ -22,6 +22,7 @@ #include "storage/condition_variable.h" #include "storage/lwlock.h" #include "storage/shmem.h" +#include "storage/pg_shmem.h" #include "storage/smgr.h" #include "storage/spin.h" #include "utils/relcache.h" diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index e0f5f92e947..c0439f2206b 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197 -- 2.45.1 --q7xzg7duksj2kgko Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v4 1/8] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 ++++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 141 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 278 insertions(+), 125 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index f7c8638aec5..b6301463ac7 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index 895a43fb39e..389abc82519 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -75,19 +75,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* @@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -118,9 +132,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -145,11 +159,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -179,6 +199,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -329,6 +367,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -345,9 +395,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -380,6 +430,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 3df29658f18..8241c061507 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..138078c29c5 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index 904a336b851..5929f140236 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); base-commit: 5e1915439085014140314979c4dd5e23bd677cac -- 2.45.1 --vninua6xybvzgrci Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v4-0002-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v5 04/10] Allow to use multiple shared memory mappings @ 2025-02-28 18:54 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw) Currently all the work with shared memory is done via a single anonymous memory mapping, which limits ways how the shared memory could be organized. Introduce possibility to allocate multiple shared memory mappings, where a single mapping is associated with a specified shared memory segment. There is only fixed amount of available segments, currently only one main shared memory segment is allocated. A new shared memory API is introduces, extended with a segment as a new parameter. As a path of least resistance, the original API is kept in place, utilizing the main shared memory segment. --- src/backend/port/posix_sema.c | 4 +- src/backend/port/sysv_sema.c | 4 +- src/backend/port/sysv_shmem.c | 138 +++++++++++++++++++--------- src/backend/port/win32_sema.c | 2 +- src/backend/storage/ipc/ipc.c | 4 +- src/backend/storage/ipc/ipci.c | 63 +++++++------ src/backend/storage/ipc/shmem.c | 148 +++++++++++++++++++++--------- src/backend/storage/lmgr/lwlock.c | 13 ++- src/include/storage/ipc.h | 2 +- src/include/storage/pg_sema.h | 2 +- src/include/storage/pg_shmem.h | 18 ++++ src/include/storage/shmem.h | 12 +++ 12 files changed, 284 insertions(+), 126 deletions(-) diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c index 269c7460817..401e1113fa1 100644 --- a/src/backend/port/posix_sema.c +++ b/src/backend/port/posix_sema.c @@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas) * we don't have to expose the counters to other processes.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); #endif numSems = 0; diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c index 423b2b4f9d6..4ce2cfb662b 100644 --- a/src/backend/port/sysv_sema.c +++ b/src/backend/port/sysv_sema.c @@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas) * have clobbered.) */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { struct stat statbuf; @@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas) * ShmemAlloc() won't be ready yet. */ sharedSemas = (PGSemaphore) - ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas)); + ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment); numSharedSemas = 0; maxSharedSemas = maxSemas; diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c index 197926d44f6..56af0231d24 100644 --- a/src/backend/port/sysv_shmem.c +++ b/src/backend/port/sysv_shmem.c @@ -94,8 +94,19 @@ typedef enum unsigned long UsedShmemSegID = 0; void *UsedShmemSegAddr = NULL; -static Size AnonymousShmemSize; -static void *AnonymousShmem = NULL; +typedef struct AnonymousMapping +{ + int shmem_segment; + Size shmem_size; /* Size of the mapping */ + Pointer shmem; /* Pointer to the start of the mapped memory */ + Pointer seg_addr; /* SysV shared memory for the header */ + unsigned long seg_id; /* IPC key */ +} AnonymousMapping; + +static AnonymousMapping Mappings[ANON_MAPPINGS]; + +/* Keeps track of used mapping segments */ +static int next_free_segment = 0; static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size); static void IpcMemoryDetach(int status, Datum shmaddr); @@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId, void *attachAt, PGShmemHeader **addr); +static const char* +MappingName(int shmem_segment) +{ + switch (shmem_segment) + { + case MAIN_SHMEM_SEGMENT: + return "main"; + default: + return "unknown"; + } +} + +static void +DebugMappings() +{ + for(int i = 0; i < next_free_segment; i++) + { + AnonymousMapping m = Mappings[i]; + elog(DEBUG1, "Mapping[%s]: addr %p, size %zu", + MappingName(i), m.shmem, m.shmem_size); + } +} /* * InternalIpcMemoryCreate(memKey, size) @@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source) /* * Creates an anonymous mmap()ed shared memory segment. * - * Pass the requested size in *size. This function will modify *size to the - * actual size of the allocation, if it ends up allocating a segment that is - * larger than requested. + * This function will modify mapping size to the actual size of the allocation, + * if it ends up allocating a segment that is larger than requested. */ -static void * -CreateAnonymousSegment(Size *size) +static void +CreateAnonymousSegment(AnonymousMapping *mapping) { - Size allocsize = *size; + Size allocsize = mapping->shmem_size; void *ptr = MAP_FAILED; int mmap_errno = 0; @@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size) PG_MMAP_FLAGS | mmap_flags, -1, 0); mmap_errno = errno; if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED) - elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", - allocsize); + { + DebugMappings(); + elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m", + MappingName(mapping->shmem_segment), allocsize); + } } #endif @@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size) * Use the original size, not the rounded-up value, when falling back * to non-huge pages. */ - allocsize = *size; + allocsize = mapping->shmem_size; ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE, PG_MMAP_FLAGS, -1, 0); mmap_errno = errno; @@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size) if (ptr == MAP_FAILED) { errno = mmap_errno; + DebugMappings(); ereport(FATAL, - (errmsg("could not map anonymous shared memory: %m"), + (errmsg("segment[%s]: could not map anonymous shared memory: %m", + MappingName(mapping->shmem_segment)), (mmap_errno == ENOMEM) ? errhint("This error usually means that PostgreSQL's request " "for a shared memory segment exceeded available memory, " @@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size) allocsize) : 0)); } - *size = allocsize; - return ptr; + mapping->shmem = ptr; + mapping->shmem_size = allocsize; } /* @@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size) static void AnonymousShmemDetach(int status, Datum arg) { - /* Release anonymous shared memory block, if any. */ - if (AnonymousShmem != NULL) + for(int i = 0; i < next_free_segment; i++) { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + AnonymousMapping m = Mappings[i]; + + /* Release anonymous shared memory block, if any. */ + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } @@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size, PGShmemHeader *hdr; struct stat statbuf; Size sysvsize; + AnonymousMapping *mapping = &Mappings[next_free_segment]; /* * We use the data directory's ID info (inode and device numbers) to @@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size, /* Room for a header? */ Assert(size > MAXALIGN(sizeof(PGShmemHeader))); + mapping->shmem_size = size; + mapping->shmem_segment = next_free_segment; if (shared_memory_type == SHMEM_TYPE_MMAP) { - AnonymousShmem = CreateAnonymousSegment(&size); - AnonymousShmemSize = size; + /* On success, mapping data will be modified. */ + CreateAnonymousSegment(mapping); + + next_free_segment++; /* Register on-exit routine to unmap the anonymous segment */ on_shmem_exit(AnonymousShmemDetach, (Datum) 0); @@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size, * loop simultaneously. (CreateDataDirLockFile() does not entirely ensure * that, but prefer fixing it over coping here.) */ - NextShmemSegID = statbuf.st_ino; + NextShmemSegID = statbuf.st_ino + next_free_segment; for (;;) { @@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size, /* * Initialize space allocation status for segment. */ - hdr->totalsize = size; + hdr->totalsize = mapping->shmem_size; hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader)); *shim = hdr; /* Save info for possible future use */ - UsedShmemSegAddr = memAddress; - UsedShmemSegID = (unsigned long) NextShmemSegID; + mapping->seg_addr = memAddress; + mapping->seg_id = (unsigned long) NextShmemSegID; /* * If AnonymousShmem is NULL here, then we're not using anonymous shared @@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size, * block. Otherwise, the System V shared memory block is only a shim, and * we must return a pointer to the real block. */ - if (AnonymousShmem == NULL) + if (mapping->shmem == NULL) return hdr; - memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader)); - return (PGShmemHeader *) AnonymousShmem; + memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader)); + return (PGShmemHeader *) mapping->shmem; } #ifdef EXEC_BACKEND @@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void) void PGSharedMemoryDetach(void) { - if (UsedShmemSegAddr != NULL) + for(int i = 0; i < next_free_segment; i++) { - if ((shmdt(UsedShmemSegAddr) < 0) + AnonymousMapping m = Mappings[i]; + + if (m.seg_addr != NULL) + { + if ((shmdt(m.seg_addr) < 0) #if defined(EXEC_BACKEND) && defined(__CYGWIN__) - /* Work-around for cygipc exec bug */ - && shmdt(NULL) < 0 + /* Work-around for cygipc exec bug */ + && shmdt(NULL) < 0 #endif - ) - elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr); - UsedShmemSegAddr = NULL; - } + ) + elog(LOG, "shmdt(%p) failed: %m", m.seg_addr); + m.seg_addr = NULL; + } - if (AnonymousShmem != NULL) - { - if (munmap(AnonymousShmem, AnonymousShmemSize) < 0) - elog(LOG, "munmap(%p, %zu) failed: %m", - AnonymousShmem, AnonymousShmemSize); - AnonymousShmem = NULL; + if (m.shmem != NULL) + { + if (munmap(m.shmem, m.shmem_size) < 0) + elog(LOG, "munmap(%p, %zu) failed: %m", + m.shmem, m.shmem_size); + m.shmem = NULL; + } } } diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c index 5854ad1f54d..e7365ff8060 100644 --- a/src/backend/port/win32_sema.c +++ b/src/backend/port/win32_sema.c @@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas) * process exits. */ void -PGReserveSemaphores(int maxSemas) +PGReserveSemaphores(int maxSemas, int shmem_segment) { mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE)); if (mySemSet == NULL) diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c index 567739b5be9..5b55bec8d9d 100644 --- a/src/backend/storage/ipc/ipc.c +++ b/src/backend/storage/ipc/ipc.c @@ -61,6 +61,8 @@ static void proc_exit_prepare(int code); * but provide some additional features we need --- in particular, * we want to register callbacks to invoke when we are disconnecting * from a broken shared-memory context but not exiting the postmaster. + * Maximum number of such exit callbacks depends on the number of shared + * segments. * * Callback functions can take zero, one, or two args: the first passed * arg is the integer exitcode, the second is the Datum supplied when @@ -68,7 +70,7 @@ static void proc_exit_prepare(int code); * ---------------------------------------------------------------- */ -#define MAX_ON_EXITS 20 +#define MAX_ON_EXITS 40 struct ONEXIT { diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..8b38e985327 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size) * required. */ Size -CalculateShmemSize(int *num_semaphores) +CalculateShmemSize(int *num_semaphores, int shmem_segment) { Size size; int numSemas; @@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void) Assert(!IsUnderPostmaster); - /* Compute the size of the shared-memory block */ - size = CalculateShmemSize(&numSemas); - elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); - - /* - * Create the shmem segment - */ - seghdr = PGSharedMemoryCreate(size, &shim); - - /* - * Make sure that huge pages are never reported as "unknown" while the - * server is running. - */ - Assert(strcmp("unknown", - GetConfigOption("huge_pages_status", false, false)) != 0); - - InitShmemAccess(seghdr); - - /* - * Create semaphores - */ - PGReserveSemaphores(numSemas); - - /* - * Set up shared memory allocation mechanism - */ - InitShmemAllocation(); + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + /* Compute the size of the shared-memory block */ + size = CalculateShmemSize(&numSemas, segment); + elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size); + + /* + * Create the shmem segment. + * + * XXX: Do multiple shims are needed, one per segment? + */ + seghdr = PGSharedMemoryCreate(size, &shim); + + /* + * Make sure that huge pages are never reported as "unknown" while the + * server is running. + */ + Assert(strcmp("unknown", + GetConfigOption("huge_pages_status", false, false)) != 0); + + InitShmemAccessInSegment(seghdr, segment); + + /* + * Create semaphores + */ + PGReserveSemaphores(numSemas, segment); + + /* + * Set up shared memory allocation mechanism + */ + InitShmemAllocationInSegment(segment); + } /* Initialize subsystems */ CreateOrAttachShmemStructs(); @@ -363,7 +368,7 @@ InitializeShmemGUCs(void) /* * Calculate the shared memory size and round up to the nearest megabyte. */ - size_b = CalculateShmemSize(&num_semas); + size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT); size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024); sprintf(buf, "%zu", size_mb); SetConfigOption("shared_memory_size", buf, diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c index c9ae3b45b76..72255a1c5ca 100644 --- a/src/backend/storage/ipc/shmem.c +++ b/src/backend/storage/ipc/shmem.c @@ -76,19 +76,19 @@ #include "utils/builtins.h" static void *ShmemAllocRaw(Size size, Size *allocated_size); +static void *ShmemAllocRawInSegment(Size size, Size *allocated_size, + int shmem_segment); /* shared memory global variables */ -static PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ +ShmemSegment Segments[ANON_MAPPINGS]; -static void *ShmemBase; /* start address of shared memory */ - -static void *ShmemEnd; /* end+1 address of shared memory */ - -slock_t *ShmemLock; /* spinlock for shared memory and LWLock - * allocation */ - -static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */ +/* + * Primary index hashtable for shmem, for simplicity we use a single for all + * shared memory segments. There can be performance consequences of that, and + * an alternative option would be to have one index per shared memory segments. + */ +static HTAB *ShmemIndex = NULL; /* To get reliable results for NUMA inquiry we need to "touch pages" once */ static bool firstNumaTouch = true; @@ -101,9 +101,17 @@ Datum pg_numa_available(PG_FUNCTION_ARGS); void InitShmemAccess(PGShmemHeader *seghdr) { - ShmemSegHdr = seghdr; - ShmemBase = seghdr; - ShmemEnd = (char *) ShmemBase + seghdr->totalsize; + InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment) +{ + PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr; + ShmemSegment *seg = &Segments[shmem_segment]; + seg->ShmemSegHdr = shmhdr; + seg->ShmemBase = (void *) shmhdr; + seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize; } /* @@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr) void InitShmemAllocation(void) { - PGShmemHeader *shmhdr = ShmemSegHdr; + InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT); +} + +void +InitShmemAllocationInSegment(int shmem_segment) +{ + PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr; char *aligned; Assert(shmhdr != NULL); @@ -123,9 +137,9 @@ InitShmemAllocation(void) * Initialize the spinlock used by ShmemAlloc. We must use * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet. */ - ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t)); + Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment); - SpinLockInit(ShmemLock); + SpinLockInit(Segments[shmem_segment].ShmemLock); /* * Allocations after this point should go through ShmemAlloc, which @@ -150,11 +164,17 @@ InitShmemAllocation(void) */ void * ShmemAlloc(Size size) +{ + return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocInSegment(Size size, int shmem_segment) { void *newSpace; Size allocated_size; - newSpace = ShmemAllocRaw(size, &allocated_size); + newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (!newSpace) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -184,6 +204,12 @@ ShmemAllocNoError(Size size) */ static void * ShmemAllocRaw(Size size, Size *allocated_size) +{ + return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT); +} + +static void * +ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment) { Size newStart; Size newFree; @@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size) size = CACHELINEALIGN(size); *allocated_size = size; - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - SpinLockAcquire(ShmemLock); + SpinLockAcquire(Segments[shmem_segment].ShmemLock); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree <= ShmemSegHdr->totalsize) + if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize) { - newSpace = (char *) ShmemBase + newStart; - ShmemSegHdr->freeoffset = newFree; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; } else newSpace = NULL; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[shmem_segment].ShmemLock); /* note this assert is okay with newSpace == NULL */ Assert(newSpace == (void *) CACHELINEALIGN(newSpace)); @@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size) */ void * ShmemAllocUnlocked(Size size) +{ + return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemAllocUnlockedInSegment(Size size, int shmem_segment) { Size newStart; Size newFree; @@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size) */ size = MAXALIGN(size); - Assert(ShmemSegHdr != NULL); + Assert(Segments[shmem_segment].ShmemSegHdr != NULL); - newStart = ShmemSegHdr->freeoffset; + newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset; newFree = newStart + size; - if (newFree > ShmemSegHdr->totalsize) + if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), errmsg("out of shared memory (%zu bytes requested)", size))); - ShmemSegHdr->freeoffset = newFree; + Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree; - newSpace = (char *) ShmemBase + newStart; + newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart; Assert(newSpace == (void *) MAXALIGN(newSpace)); @@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size) bool ShmemAddrIsValid(const void *addr) { - return (addr >= ShmemBase) && (addr < ShmemEnd); + return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT); +} + +bool +ShmemAddrIsValidInSegment(const void *addr, int shmem_segment) +{ + return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd); } /* @@ -334,6 +372,18 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ long max_size, /* max size of the table */ HASHCTL *infoP, /* info about key and bucket size */ int hash_flags) /* info about infoP */ +{ + return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags, + MAIN_SHMEM_SEGMENT); +} + +HTAB * +ShmemInitHashInSegment(const char *name, /* table string name for shmem index */ + long init_size, /* initial table size */ + long max_size, /* max size of the table */ + HASHCTL *infoP, /* info about key and bucket size */ + int hash_flags, /* info about infoP */ + int shmem_segment) /* in which segment to keep the table */ { bool found; void *location; @@ -350,9 +400,9 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE; /* look it up in the shmem index */ - location = ShmemInitStruct(name, + location = ShmemInitStructInSegment(name, hash_get_shared_size(infoP, hash_flags), - &found); + &found, shmem_segment); /* * if it already exists, attach to it rather than allocate and initialize @@ -385,6 +435,13 @@ ShmemInitHash(const char *name, /* table string name for shmem index */ */ void * ShmemInitStruct(const char *name, Size size, bool *foundPtr) +{ + return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT); +} + +void * +ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr, + int shmem_segment) { ShmemIndexEnt *result; void *structPtr; @@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) if (!ShmemIndex) { - PGShmemHeader *shmemseghdr = ShmemSegHdr; + PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr; /* Must be trying to create/attach to ShmemIndex itself */ Assert(strcmp(name, "ShmemIndex") == 0); @@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) * process can be accessing shared memory yet. */ Assert(shmemseghdr->index == NULL); - structPtr = ShmemAlloc(size); + structPtr = ShmemAllocInSegment(size, shmem_segment); shmemseghdr->index = structPtr; *foundPtr = false; } @@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("could not create ShmemIndex entry for data structure \"%s\"", - name))); + errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d", + name, shmem_segment))); } if (*foundPtr) @@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) Size allocated_size; /* It isn't in the table yet. allocate and initialize it */ - structPtr = ShmemAllocRaw(size, &allocated_size); + structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment); if (structPtr == NULL) { /* out of memory; remove the failed ShmemIndex entry */ @@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr) LWLockRelease(ShmemIndexLock); - Assert(ShmemAddrIsValid(structPtr)); + Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment)); Assert(structPtr == (void *) CACHELINEALIGN(structPtr)); return structPtr; } - /* * Add two Size values, checking for overflow */ @@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output all allocated entries */ memset(nulls, 0, sizeof(nulls)); + /* XXX: take all shared memory segments into account. */ while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL) { values[0] = CStringGetTextDatum(ent->key); - values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr); + values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr); values[2] = Int64GetDatum(ent->size); values[3] = Int64GetDatum(ent->allocated_size); named_allocated += ent->allocated_size; @@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS) /* output shared memory allocated but not counted via the shmem index */ values[0] = CStringGetTextDatum("<anonymous>"); nulls[1] = true; - values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); /* output as-of-yet unused shared memory */ nulls[0] = true; - values[1] = Int64GetDatum(ShmemSegHdr->freeoffset); + values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); nulls[1] = false; - values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset); + values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset); values[3] = values[2]; tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS) * this is not very likely, and moreover we have more entries, each of * them using only fraction of the total pages. */ - shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1; + for(int segment = 0; segment < ANON_MAPPINGS; segment++) + { + PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr; + shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1; + } + page_ptrs = palloc0(sizeof(void *) * shm_total_page_count); pages_status = palloc(sizeof(int) * shm_total_page_count); diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c index 46f44bc4511..a36b08895c8 100644 --- a/src/backend/storage/lmgr/lwlock.c +++ b/src/backend/storage/lmgr/lwlock.c @@ -80,6 +80,8 @@ #include "pg_trace.h" #include "pgstat.h" #include "port/pg_bitutils.h" +#include "postmaster/postmaster.h" +#include "storage/pg_shmem.h" #include "storage/proc.h" #include "storage/proclist.h" #include "storage/procnumber.h" @@ -618,10 +620,15 @@ LWLockNewTrancheId(void) int *LWLockCounter; LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int)); - /* We use the ShmemLock spinlock to protect LWLockCounter */ - SpinLockAcquire(ShmemLock); + /* + * We use the ShmemLock spinlock to protect LWLockCounter. + * + * XXX: Looks like this is the only use of Segments outside of shmem.c, + * it's maybe worth it to reshape this part to hide Segments structure. + */ + SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); result = (*LWLockCounter)++; - SpinLockRelease(ShmemLock); + SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock); return result; } diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h index 3baf418b3d1..6ebda479ced 100644 --- a/src/include/storage/ipc.h +++ b/src/include/storage/ipc.h @@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void); /* ipci.c */ extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook; -extern Size CalculateShmemSize(int *num_semaphores); +extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment); extern void CreateSharedMemoryAndSemaphores(void); #ifdef EXEC_BACKEND extern void AttachSharedMemoryStructs(void); diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h index fa6ca35a51f..8ae9637fcd0 100644 --- a/src/include/storage/pg_sema.h +++ b/src/include/storage/pg_sema.h @@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore; extern Size PGSemaphoreShmemSize(int maxSemas); /* Module initialization (called during postmaster start or shmem reinit) */ -extern void PGReserveSemaphores(int maxSemas); +extern void PGReserveSemaphores(int maxSemas, int shmem_segment); /* Allocate a PGSemaphore structure with initial count 1 */ extern PGSemaphore PGSemaphoreCreate(void); diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index 5f7d4b83a60..2348c59b5a0 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -25,6 +25,7 @@ #define PG_SHMEM_H #include "storage/dsm_impl.h" +#include "storage/spin.h" typedef struct PGShmemHeader /* standard header for all Postgres shmem */ { @@ -41,6 +42,20 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ #endif } PGShmemHeader; +typedef struct ShmemSegment +{ + PGShmemHeader *ShmemSegHdr; /* shared mem segment header */ + void *ShmemBase; /* start address of shared memory */ + void *ShmemEnd; /* end+1 address of shared memory */ + slock_t *ShmemLock; /* spinlock for shared memory and LWLock + * allocation */ +} ShmemSegment; + +/* Number of available segments for anonymous memory mappings */ +#define ANON_MAPPINGS 1 + +extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS]; + /* GUC variables */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; @@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2); extern void PGSharedMemoryDetach(void); extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags); +/* The main segment, contains everything except buffer blocks and related data. */ +#define MAIN_SHMEM_SEGMENT 0 + #endif /* PG_SHMEM_H */ diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h index c1f668ded95..69663d412c3 100644 --- a/src/include/storage/shmem.h +++ b/src/include/storage/shmem.h @@ -29,15 +29,27 @@ extern PGDLLIMPORT slock_t *ShmemLock; struct PGShmemHeader; /* avoid including storage/pg_shmem.h here */ extern void InitShmemAccess(struct PGShmemHeader *seghdr); +extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr, + int shmem_segment); extern void InitShmemAllocation(void); +extern void InitShmemAllocationInSegment(int shmem_segment); extern void *ShmemAlloc(Size size); +extern void *ShmemAllocInSegment(Size size, int shmem_segment); extern void *ShmemAllocNoError(Size size); extern void *ShmemAllocUnlocked(Size size); +extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment); extern bool ShmemAddrIsValid(const void *addr); +extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment); extern void InitShmemIndex(void); +extern void InitVariableShmemIndex(void); extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size, HASHCTL *infoP, int hash_flags); +extern HTAB *ShmemInitHashInSegment(const char *name, long init_size, + long max_size, HASHCTL *infoP, + int hash_flags, int shmem_segment); extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr); +extern void *ShmemInitStructInSegment(const char *name, Size size, + bool *foundPtr, int shmem_segment); extern Size add_size(Size s1, Size s2); extern Size mul_size(Size s1, Size s2); -- 2.49.0 --bwrlgp6w2ubxykjq Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="v5-0005-Address-space-reservation-for-shared-memory.patch" ^ permalink raw reply [nested|flat] 309+ messages in thread
* [PATCH v11a 2/2] ci: Remove support for cirrus-ci based CI @ 2026-06-04 13:34 Andres Freund <[email protected]> 0 siblings, 0 replies; 309+ messages in thread From: Andres Freund @ 2026-06-04 13:34 UTC (permalink / raw) As mentioned in the earlier commit, cirrus-ci has shut down. Therefore remove all files related to running CI via cirrus. Also update comments / code that were referencing cirrus-ci. Discussion: https://postgr.es/m/3ydjipcr7kbss57nvi67noplncqhesl5eyb6wgol4ccjxynspv%40yatlykpribmm --- src/bin/pg_combinebackup/t/010_hardlink.pl | 12 +- .cirrus.yml | 91 -- src/test/perl/PostgreSQL/Test/Cluster.pm | 5 +- .cirrus.star | 143 --- .cirrus.tasks.yml | 1022 -------------------- src/tools/ci/ci_macports_packages.sh | 7 +- src/tools/ci/gcp_ram_disk.sh | 27 - 7 files changed, 11 insertions(+), 1296 deletions(-) delete mode 100644 .cirrus.yml delete mode 100644 .cirrus.star delete mode 100644 .cirrus.tasks.yml delete mode 100755 src/tools/ci/gcp_ram_disk.sh diff --git a/src/bin/pg_combinebackup/t/010_hardlink.pl b/src/bin/pg_combinebackup/t/010_hardlink.pl index b6e8a9128af..5fbbe6a923b 100644 --- a/src/bin/pg_combinebackup/t/010_hardlink.pl +++ b/src/bin/pg_combinebackup/t/010_hardlink.pl @@ -18,13 +18,13 @@ $primary->append_conf('postgresql.conf', 'autovacuum = off'); $primary->start; # Create a couple of tables (~264KB each). -# Note: Cirrus CI runs some tests with a very small segment size, so, in that +# Note: CI runs some tests with a very small segment size, so, in that # environment, a single table of 264KB would have both a segment with a link -# count of 1 and also one with a link count of 2. But in a normal installation, -# segment size is 1GB. Therefore, we use 2 different tables here: for test_1, -# all segments (or the only one) will have two hard links; for test_2, the -# last segment (or the only one) will have 1 hard link, and any others will -# have 2. +# count of 1 and also one with a link count of 2. But in a normal +# installation, segment size is 1GB. Therefore, we use 2 different tables +# here: for test_1, all segments (or the only one) will have two hard links; +# for test_2, the last segment (or the only one) will have 1 hard link, and +# any others will have 2. my $query = <<'EOM'; CREATE TABLE test_%s AS SELECT x.id::bigint, diff --git a/.cirrus.yml b/.cirrus.yml deleted file mode 100644 index 3f75852e84e..00000000000 --- a/.cirrus.yml +++ /dev/null @@ -1,91 +0,0 @@ -# CI configuration file for CI utilizing cirrus-ci.org -# -# For instructions on how to enable the CI integration in a repository and -# further details, see src/tools/ci/README -# -# -# The actual CI tasks are defined in .cirrus.tasks.yml. To make the compute -# resources for CI configurable on a repository level, the "final" CI -# configuration is the combination of: -# -# 1) the contents of this file -# -# 2) computed environment variables -# -# Used to enable/disable tasks based on the execution environment. See -# .cirrus.star: compute_environment_vars() -# -# 3) if defined, the contents of the file referenced by the, repository -# level, REPO_CI_CONFIG_GIT_URL variable (see -# https://cirrus-ci.org/guide/programming-tasks/#fs for the accepted -# format) -# -# This allows running tasks in a different execution environment than the -# default, e.g. to have sufficient resources for cfbot. -# -# 4) .cirrus.tasks.yml -# -# This composition is done by .cirrus.star - - -env: - # Source of images / containers - GCP_PROJECT: pg-ci-images - IMAGE_PROJECT: $GCP_PROJECT - CONTAINER_REPO: us-docker.pkg.dev/${GCP_PROJECT}/ci - DISK_SIZE: 25 - - -# Define how to run various types of tasks. - -# VMs provided by cirrus-ci. Each user has a limited number of "free" credits -# for testing. -cirrus_community_vm_template: &cirrus_community_vm_template - compute_engine_instance: - image_project: $IMAGE_PROJECT - image: family/$IMAGE_FAMILY - platform: $PLATFORM - cpu: $CPUS - disk: $DISK_SIZE - - -default_linux_task_template: &linux_task_template - env: - PLATFORM: linux - <<: *cirrus_community_vm_template - - -default_freebsd_task_template: &freebsd_task_template - env: - PLATFORM: freebsd - <<: *cirrus_community_vm_template - -default_netbsd_task_template: &netbsd_task_template - env: - PLATFORM: netbsd - <<: *cirrus_community_vm_template - -default_openbsd_task_template: &openbsd_task_template - env: - PLATFORM: openbsd - <<: *cirrus_community_vm_template - - -default_windows_task_template: &windows_task_template - env: - PLATFORM: windows - <<: *cirrus_community_vm_template - - -# macos workers provided by cirrus-ci -default_macos_task_template: &macos_task_template - env: - PLATFORM: macos - macos_instance: - image: $IMAGE - - -# Contents of REPO_CI_CONFIG_GIT_URL, if defined, will be inserted here, -# followed by the contents .cirrus.tasks.yml. This allows -# REPO_CI_CONFIG_GIT_URL to override how the task types above will be -# executed, e.g. using a custom compute account or permanent workers. diff --git a/src/test/perl/PostgreSQL/Test/Cluster.pm b/src/test/perl/PostgreSQL/Test/Cluster.pm index 4fcb1f6be56..529f49efee1 100644 --- a/src/test/perl/PostgreSQL/Test/Cluster.pm +++ b/src/test/perl/PostgreSQL/Test/Cluster.pm @@ -363,9 +363,8 @@ This tries to connect to the server, to test whether it works or not,, so the server is up and running. Otherwise this can return 0 even if there's nothing wrong with raw_connect() itself. -Notably, raw_connect() does not work on Unix domain sockets on -Strawberry perl 5.26.3.1 on Windows, which we use in Cirrus CI images -as of this writing. It dies with "not implemented on this +Notably, raw_connect() does not work on Unix domain sockets on at least +Strawberry perl 5.26.3.1 on Windows. It dies with "not implemented on this architecture". =cut diff --git a/.cirrus.star b/.cirrus.star deleted file mode 100644 index e9bb672b959..00000000000 --- a/.cirrus.star +++ /dev/null @@ -1,143 +0,0 @@ -"""Additional CI configuration, using the starlark language. See -https://cirrus-ci.org/guide/programming-tasks/#introduction-into-starlark - -See also the starlark specification at -https://github.com/bazelbuild/starlark/blob/master/spec.md - -See also .cirrus.yml and src/tools/ci/README -""" - -load("cirrus", "env", "fs", "re", "yaml") - - -def main(): - """The main function is executed by cirrus-ci after loading .cirrus.yml and can - extend the CI definition further. - - As documented in .cirrus.yml, the final CI configuration is composed of - - 1) the contents of .cirrus.yml - - 2) computed environment variables - - 3) if defined, the contents of the file referenced by the, repository - level, REPO_CI_CONFIG_GIT_URL variable (see - https://cirrus-ci.org/guide/programming-tasks/#fs for the accepted - format) - - 4) .cirrus.tasks.yml - """ - - output = "" - - # 1) is evaluated implicitly - - - # Add 2) - additional_env = compute_environment_vars() - env_fmt = """ -### -# Computed environment variables start here -### -{0} -### -# Computed environment variables end here -### -""" - output += env_fmt.format(yaml.dumps({'env': additional_env})) - - - # Add 3) - repo_config_url = env.get("REPO_CI_CONFIG_GIT_URL") - if repo_config_url != None: - print("loading additional configuration from \"{}\"".format(repo_config_url)) - output += config_from(repo_config_url) - else: - output += "\n# REPO_CI_CONFIG_URL was not set\n" - - - # Add 4) - output += config_from(".cirrus.tasks.yml") - - - return output - - -def compute_environment_vars(): - cenv = {} - - ### - # Some tasks are manually triggered by default because they might use too - # many resources for users of free Cirrus credits, but they can be - # triggered automatically by naming them in an environment variable e.g. - # REPO_CI_AUTOMATIC_TRIGGER_TASKS="task_name other_task" under "Repository - # Settings" on Cirrus CI's website. - - default_manual_trigger_tasks = ['mingw', 'netbsd', 'openbsd'] - - repo_ci_automatic_trigger_tasks = env.get('REPO_CI_AUTOMATIC_TRIGGER_TASKS', '') - for task in default_manual_trigger_tasks: - name = 'CI_TRIGGER_TYPE_' + task.upper() - if repo_ci_automatic_trigger_tasks.find(task) != -1: - value = 'automatic' - else: - value = 'manual' - cenv[name] = value - ### - - ### - # Parse "ci-os-only:" tag in commit message and set - # CI_{$OS}_ENABLED variable for each OS - - # We want to disable SanityCheck if testing just a specific OS. This - # shortens push-wait-for-ci cycle time a bit when debugging operating - # system specific failures. Just treating it as an OS in that case - # suffices. - - operating_systems = [ - 'compilerwarnings', - 'freebsd', - 'linux', - 'macos', - 'mingw', - 'netbsd', - 'openbsd', - 'sanitycheck', - 'windows', - ] - commit_message = env.get('CIRRUS_CHANGE_MESSAGE') - match_re = r"(^|.*\n)ci-os-only: ([^\n]+)($|\n.*)" - - # re.match() returns an array with a tuple of (matched-string, match_1, ...) - m = re.match(match_re, commit_message) - if m and len(m) > 0: - os_only = m[0][2] - os_only_list = re.split(r'[, ]+', os_only) - else: - os_only_list = operating_systems - - for os in operating_systems: - os_enabled = os in os_only_list - cenv['CI_{0}_ENABLED'.format(os.upper())] = os_enabled - ### - - return cenv - - -def config_from(config_src): - """return contents of config file `config_src`, surrounded by markers - indicating start / end of the included file - """ - - config_contents = fs.read(config_src) - config_fmt = """ - -### -# contents of config file `{0}` start here -### -{1} -### -# contents of config file `{0}` end here -### -""" - return config_fmt.format(config_src, config_contents) diff --git a/.cirrus.tasks.yml b/.cirrus.tasks.yml deleted file mode 100644 index 8683d1ae9c7..00000000000 --- a/.cirrus.tasks.yml +++ /dev/null @@ -1,1022 +0,0 @@ -# CI configuration file for CI utilizing cirrus-ci.org -# -# For instructions on how to enable the CI integration in a repository and -# further details, see src/tools/ci/README -# -# -# NB: Different tasks intentionally test with different, non-default, -# configurations, to increase the chance of catching problems. Each task with -# non-obvious non-default documents their oddity at the top of the task, -# prefixed by "SPECIAL:". - - -env: - # The lower depth accelerates git clone. Use a bit of depth so that - # concurrent tasks and retrying older jobs have a chance of working. - CIRRUS_CLONE_DEPTH: 500 - # Useful to be able to analyse what in a script takes long - CIRRUS_LOG_TIMESTAMP: true - - CCACHE_MAXSIZE: "250M" - - # target to test, for all but windows - CHECK: check-world PROVE_FLAGS=$PROVE_FLAGS - CHECKFLAGS: -Otarget - PROVE_FLAGS: --timer - # Build test dependencies as part of the build step, to see compiler - # errors/warnings in one place. - MBUILD_TARGET: all testprep - MTEST_ARGS: --print-errorlogs --no-rebuild -C build - PGCTLTIMEOUT: 120 # avoids spurious failures during parallel tests - TEMP_CONFIG: ${CIRRUS_WORKING_DIR}/src/tools/ci/pg_ci_base.conf - PG_TEST_EXTRA: kerberos ldap ssl libpq_encryption load_balance oauth - - # Postgres config args for the meson builds, shared between all meson tasks - # except the 'SanityCheck' task - MESON_COMMON_PG_CONFIG_ARGS: -Dcassert=true -Dinjection_points=true - - # Meson feature flags shared by all meson tasks, except: - # SanityCheck: uses almost no dependencies. - # Windows - VS: has fewer dependencies than listed here, so defines its own. - # Linux: uses the 'auto' feature option to test meson feature autodetection. - MESON_COMMON_FEATURES: >- - -Dauto_features=disabled - -Dldap=enabled - -Dssl=openssl - -Dtap_tests=enabled - -Dplperl=enabled - -Dplpython=enabled - -Ddocs=enabled - -Dicu=enabled - -Dlibxml=enabled - -Dlibxslt=enabled - -Dlz4=enabled - -Dpltcl=enabled - -Dreadline=enabled - -Dzlib=enabled - -Dzstd=enabled - - -# What files to preserve in case tests fail -on_failure_ac: &on_failure_ac - log_artifacts: - paths: - - "**/*.log" - - "**/*.diffs" - - "**/regress_log_*" - type: text/plain - -on_failure_meson: &on_failure_meson - testrun_artifacts: - paths: - - "build*/testrun/**/*.log" - - "build*/testrun/**/*.diffs" - - "build*/testrun/**/regress_log_*" - type: text/plain - - # In theory it'd be nice to upload the junit files meson generates, so that - # cirrus will nicely annotate the commit. Unfortunately the files don't - # contain identifiable file + line numbers right now, so the annotations - # don't end up useful. We could probably improve on that with a some custom - # conversion script, but ... - meson_log_artifacts: - path: "build*/meson-logs/*.txt" - type: text/plain - - -# To avoid unnecessarily spinning up a lot of VMs / containers for entirely -# broken commits, have a minimal task that all others depend on. -# -# SPECIAL: -# - Builds with --auto-features=disabled and thus almost no enabled -# dependencies -task: - name: SanityCheck - - # If a specific OS is requested, don't run the sanity check. This shortens - # push-wait-for-ci cycle time a bit when debugging operating system specific - # failures. Uses skip instead of only_if, as cirrus otherwise warns about - # only_if conditions not matching. - skip: $CI_SANITYCHECK_ENABLED == false - - env: - CPUS: 4 - BUILD_JOBS: 8 - TEST_JOBS: 8 - IMAGE_FAMILY: pg-ci-trixie - CCACHE_DIR: ${CIRRUS_WORKING_DIR}/ccache_dir - # no options enabled, should be small - CCACHE_MAXSIZE: "150M" - - # While containers would start up a bit quicker, building is a bit - # slower. This way we don't have to maintain a container image. - <<: *linux_task_template - - ccache_cache: - folder: $CCACHE_DIR - - create_user_script: | - useradd -m postgres - chown -R postgres:postgres . - mkdir -p ${CCACHE_DIR} - chown -R postgres:postgres ${CCACHE_DIR} - echo '* - memlock 134217728' > /etc/security/limits.d/postgres.conf - su postgres -c "ulimit -l -H && ulimit -l -S" - # Can't change container's kernel.core_pattern. Postgres user can't write - # to / normally. Change that. - chown root:postgres / - chmod g+rwx / - - configure_script: | - su postgres <<-EOF - set -e - meson setup \ - --buildtype=debug \ - --auto-features=disabled \ - -Ddefault_library=shared \ - -Dtap_tests=enabled \ - build - EOF - build_script: | - su postgres <<-EOF - set -e - ninja -C build -j${BUILD_JOBS} ${MBUILD_TARGET} - EOF - upload_caches: ccache - - # Run a minimal set of tests. The main regression tests take too long for - # this purpose. For now this is a random quick pg_regress style test, and a - # tap test that exercises both a frontend binary and the backend. - test_minimal_script: | - su postgres <<-EOF - set -e - ulimit -c unlimited - meson test $MTEST_ARGS --suite setup - meson test $MTEST_ARGS --num-processes ${TEST_JOBS} \ - cube/regress pg_ctl/001_start_stop - EOF - - on_failure: - <<: *on_failure_meson - cores_script: | - mkdir -m 770 /tmp/cores - find / -maxdepth 1 -type f -name 'core*' -exec mv '{}' /tmp/cores/ \; - src/tools/ci/cores_backtrace.sh linux /tmp/cores - - -# SPECIAL: -# - Uses postgres specific CPPFLAGS that increase test coverage -# - Specifies configuration options that test reading/writing/copying of node trees -# - Specifies debug_parallel_query=regress, to catch related issues during CI -# - Also runs tests against a running postgres instance, see test_running_script -task: - name: FreeBSD - Meson - - env: - CPUS: 4 - BUILD_JOBS: 4 - TEST_JOBS: 8 - IMAGE_FAMILY: pg-ci-freebsd - DISK_SIZE: 50 - - CCACHE_DIR: /tmp/ccache_dir - CPPFLAGS: -DRELCACHE_FORCE_RELEASE -DENFORCE_REGRESSION_TEST_NAME_RESTRICTIONS - CFLAGS: -Og -ggdb - - # Several buildfarm animals enable these options. Without testing them - # during CI, it would be easy to cause breakage on the buildfarm with CI - # passing. - PG_TEST_INITDB_EXTRA_OPTS: >- - -c debug_copy_parse_plan_trees=on - -c debug_write_read_parse_plan_trees=on - -c debug_raw_expression_coverage_test=on - -c debug_parallel_query=regress - PG_TEST_PG_UPGRADE_MODE: --link - - MESON_FEATURES: >- - -Ddtrace=enabled - -Dgssapi=enabled - -Dlibcurl=enabled - -Dnls=enabled - -Dpam=enabled - -Dtcl_version=tcl86 - -Duuid=bsd - - <<: *freebsd_task_template - - depends_on: SanityCheck - only_if: $CI_FREEBSD_ENABLED - - sysinfo_script: | - id - uname -a - ulimit -a -H && ulimit -a -S - export - - ccache_cache: - folder: $CCACHE_DIR - setup_ram_disk_script: src/tools/ci/gcp_ram_disk.sh - create_user_script: | - pw useradd postgres - chown -R postgres:postgres . - mkdir -p ${CCACHE_DIR} - chown -R postgres:postgres ${CCACHE_DIR} - setup_core_files_script: | - mkdir -m 770 /tmp/cores - chown root:postgres /tmp/cores - sysctl kern.corefile='/tmp/cores/%N.%P.core' - setup_additional_packages_script: | - #pkg install -y ... - - # NB: Intentionally build without -Dllvm. The freebsd image size is already - # large enough to make VM startup slow, and even without llvm freebsd - # already takes longer than other platforms except for windows. - configure_script: | - su postgres <<-EOF - set -e - meson setup \ - ${MESON_COMMON_PG_CONFIG_ARGS} \ - --buildtype=debug \ - -Dextra_lib_dirs=/usr/local/lib -Dextra_include_dirs=/usr/local/include/ \ - ${MESON_COMMON_FEATURES} ${MESON_FEATURES} \ - build - EOF - build_script: su postgres -c 'ninja -C build -j${BUILD_JOBS} ${MBUILD_TARGET}' - upload_caches: ccache - - test_world_script: | - su postgres <<-EOF - set -e - ulimit -c unlimited - meson test $MTEST_ARGS --num-processes ${TEST_JOBS} - EOF - - # test runningcheck, freebsd chosen because it's currently fast enough - test_running_script: | - su postgres <<-EOF - set -e - ulimit -c unlimited - meson test $MTEST_ARGS --quiet --suite setup - export LD_LIBRARY_PATH="$(pwd)/build/tmp_install/usr/local/pgsql/lib/:$LD_LIBRARY_PATH" - mkdir -p build/testrun - build/tmp_install/usr/local/pgsql/bin/initdb -N build/runningcheck --no-instructions -A trust - echo "include '$(pwd)/src/tools/ci/pg_ci_base.conf'" >> build/runningcheck/postgresql.conf - build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start - meson test $MTEST_ARGS --num-processes ${TEST_JOBS} --setup running - build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop - EOF - - on_failure: - # if the server continues running, it often causes cirrus-ci to fail - # during upload, as it doesn't expect artifacts to change size - stop_running_script: | - su postgres <<-EOF - set -e - build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop || true - EOF - <<: *on_failure_meson - cores_script: src/tools/ci/cores_backtrace.sh freebsd /tmp/cores - - -task: - depends_on: SanityCheck - - env: - # Below are experimentally derived to be a decent choice. - CPUS: 4 - BUILD_JOBS: 8 - TEST_JOBS: 8 - - # Default working directory is /tmp, but its total size (1.2 GB) is not - # enough, so different working and cache directory are set. - CIRRUS_WORKING_DIR: /home/postgres/postgres - CCACHE_DIR: /home/postgres/cache - - PATH: /usr/sbin:$PATH - CORE_DUMP_DIR: /var/crash - - matrix: - - name: NetBSD - Meson - # See REPO_CI_AUTOMATIC_TRIGGER_TASKS in .cirrus.star - trigger_type: $CI_TRIGGER_TYPE_NETBSD - only_if: $CI_NETBSD_ENABLED - env: - OS_NAME: netbsd - IMAGE_FAMILY: pg-ci-netbsd-postgres - PKGCONFIG_PATH: '/usr/lib/pkgconfig:/usr/pkg/lib/pkgconfig' - # initdb fails with: 'invalid locale settings' error on NetBSD. - # Force 'LANG' and 'LC_*' variables to be 'C'. - # See https://postgr.es/m/2490325.1734471752%40sss.pgh.pa.us - LANG: "C" - LC_ALL: "C" - # -Duuid is not set for the NetBSD, see the comment below, above - # configure_script, for more information. - MESON_FEATURES: >- - -Dgssapi=enabled - -Dlibcurl=enabled - -Dnls=enabled - -Dpam=enabled - - setup_additional_packages_script: | - #pkgin -y install ... - <<: *netbsd_task_template - - - name: OpenBSD - Meson - # See REPO_CI_AUTOMATIC_TRIGGER_TASKS in .cirrus.star - trigger_type: $CI_TRIGGER_TYPE_OPENBSD - only_if: $CI_OPENBSD_ENABLED - env: - OS_NAME: openbsd - IMAGE_FAMILY: pg-ci-openbsd-postgres - PKGCONFIG_PATH: '/usr/lib/pkgconfig:/usr/local/lib/pkgconfig' - CORE_DUMP_EXECUTABLE_DIR: $CIRRUS_WORKING_DIR/build/tmp_install/usr/local/pgsql/bin - - MESON_FEATURES: >- - -Dbsd_auth=enabled - -Dlibcurl=enabled - -Dtcl_version=tcl86 - -Duuid=e2fs - - setup_additional_packages_script: | - #pkg_add -I ... - # Always core dump to ${CORE_DUMP_DIR} - set_core_dump_script: sysctl -w kern.nosuidcoredump=2 - <<: *openbsd_task_template - - sysinfo_script: | - locale - id - uname -a - ulimit -a -H && ulimit -a -S - env - - ccache_cache: - folder: $CCACHE_DIR - setup_ram_disk_script: src/tools/ci/gcp_ram_disk.sh - create_user_script: | - useradd postgres - chown -R postgres:users /home/postgres - mkdir -p ${CCACHE_DIR} - chown -R postgres:users ${CCACHE_DIR} - setup_core_files_script: | - mkdir -p ${CORE_DUMP_DIR} - chmod -R 770 ${CORE_DUMP_DIR} - chown -R postgres:users ${CORE_DUMP_DIR} - - # -Duuid=bsd is not set since 'bsd' uuid option - # is not working on NetBSD & OpenBSD. See - # https://www.postgresql.org/message-id/[email protected] - # And other uuid options are not available on NetBSD. - configure_script: | - su postgres <<-EOF - set -e - meson setup \ - ${MESON_COMMON_PG_CONFIG_ARGS} \ - --buildtype=debugoptimized \ - --pkg-config-path ${PKGCONFIG_PATH} \ - ${MESON_COMMON_FEATURES} ${MESON_FEATURES} \ - build - EOF - - build_script: su postgres -c 'ninja -C build -j${BUILD_JOBS} ${MBUILD_TARGET}' - upload_caches: ccache - - test_world_script: | - su postgres <<-EOF - set -e - ulimit -c unlimited - meson test $MTEST_ARGS --num-processes ${TEST_JOBS} - EOF - - on_failure: - <<: *on_failure_meson - cores_script: | - # Although we try to configure the OS to core dump inside - # ${CORE_DUMP_DIR}, they may not obey this. So, move core files to the - # ${CORE_DUMP_DIR} directory. - find build/ -type f -name '*.core' -exec mv '{}' ${CORE_DUMP_DIR} \; - src/tools/ci/cores_backtrace.sh ${OS_NAME} ${CORE_DUMP_DIR} ${CORE_DUMP_EXECUTABLE_DIR} - - -# configure feature flags, shared between the task running the linux tests and -# the CompilerWarnings task -LINUX_CONFIGURE_FEATURES: &LINUX_CONFIGURE_FEATURES >- - --with-gssapi - --with-icu - --with-ldap - --with-libcurl - --with-libxml - --with-libxslt - --with-llvm - --with-lz4 - --with-pam - --with-perl - --with-python - --with-selinux - --with-ssl=openssl - --with-systemd - --with-tcl --with-tclconfig=/usr/lib/tcl8.6/ - --with-uuid=ossp - --with-zstd - - -# Check SPECIAL in the matrix: below -task: - env: - CPUS: 4 - BUILD_JOBS: 4 - TEST_JOBS: 8 # experimentally derived to be a decent choice - IMAGE_FAMILY: pg-ci-trixie - - CCACHE_DIR: /tmp/ccache_dir - DEBUGINFOD_URLS: "https://debuginfod.debian.net"; - - # Enable a reasonable set of sanitizers. Use the linux task for that, as - # it's one of the fastest tasks (without sanitizers). Also several of the - # sanitizers work best on linux. - # - # The overhead of alignment sanitizer is low, undefined behaviour has - # moderate overhead. Test alignment sanitizer in the meson task, as it - # does both 32 and 64 bit builds and is thus more likely to expose - # alignment bugs. - # - # Address sanitizer in contrast is somewhat expensive. Enable it in the - # autoconf task, as the meson task tests both 32 and 64bit. - # - # disable_coredump=0, abort_on_error=1: for useful backtraces in case of crashes - # print_stacktraces=1,verbosity=2, duh - # detect_leaks=0: too many uninteresting leak errors in short-lived binaries - UBSAN_OPTIONS: print_stacktrace=1:disable_coredump=0:abort_on_error=1:verbosity=2 - ASAN_OPTIONS: print_stacktrace=1:disable_coredump=0:abort_on_error=1:detect_leaks=0 - - # SANITIZER_FLAGS is set in the tasks below - CFLAGS: -Og -ggdb -fno-sanitize-recover=all $SANITIZER_FLAGS - CXXFLAGS: $CFLAGS - LDFLAGS: $SANITIZER_FLAGS - CC: ccache gcc - CXX: ccache g++ - - LINUX_CONFIGURE_FEATURES: *LINUX_CONFIGURE_FEATURES - LINUX_MESON_FEATURES: >- - -Duuid=e2fs - - <<: *linux_task_template - - depends_on: SanityCheck - only_if: $CI_LINUX_ENABLED - - ccache_cache: - folder: ${CCACHE_DIR} - - sysinfo_script: | - id - uname -a - cat /proc/cmdline - ulimit -a -H && ulimit -a -S - export - create_user_script: | - useradd -m postgres - chown -R postgres:postgres . - mkdir -p ${CCACHE_DIR} - chown -R postgres:postgres ${CCACHE_DIR} - echo '* - memlock 134217728' > /etc/security/limits.d/postgres.conf - su postgres -c "ulimit -l -H && ulimit -l -S" - setup_core_files_script: | - mkdir -m 770 /tmp/cores - chown root:postgres /tmp/cores - sysctl kernel.core_pattern='/tmp/cores/%e-%s-%p.core' - - setup_hosts_file_script: | - cat >> /etc/hosts <<-EOF - 127.0.0.1 pg-loadbalancetest - 127.0.0.2 pg-loadbalancetest - 127.0.0.3 pg-loadbalancetest - EOF - - setup_additional_packages_script: | - #apt-get update - #DEBIAN_FRONTEND=noninteractive apt-get -y install ... - - matrix: - # SPECIAL: - # - Uses address sanitizer, sanitizer failures are typically printed in - # the server log - # - Configures postgres with a small segment size - - name: Linux - Debian Trixie - Autoconf - - env: - SANITIZER_FLAGS: -fsanitize=address - PG_TEST_PG_COMBINEBACKUP_MODE: --copy-file-range - - # Normally, the "relation segment" code basically has no coverage in our - # tests, because we (quite reasonably) don't generate tables large - # enough in tests. We've had plenty bugs that we didn't notice due the - # code not being exercised much. Thus specify a very small segment size - # here. Use a non-power-of-two segment size, given we currently allow - # that. - configure_script: | - su postgres <<-EOF - set -e - ./configure \ - --enable-cassert --enable-injection-points --enable-debug \ - --enable-tap-tests --enable-nls \ - --with-segsize-blocks=6 \ - --with-libnuma \ - --with-liburing \ - \ - ${LINUX_CONFIGURE_FEATURES} \ - \ - CLANG="ccache clang" - EOF - build_script: su postgres -c "make -s -j${BUILD_JOBS} world-bin" - upload_caches: ccache - - test_world_script: | - su postgres <<-EOF - set -e - ulimit -c unlimited # default is 0 - make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS} - EOF - - on_failure: - <<: *on_failure_ac - - # SPECIAL: - # - Uses undefined behaviour and alignment sanitizers, sanitizer failures - # are typically printed in the server log - # - Test both 64bit and 32 bit builds - # - uses io_method=io_uring - # - Uses meson feature autodetection - - name: Linux - Debian Trixie - Meson - - env: - CCACHE_MAXSIZE: "400M" # tests two different builds - SANITIZER_FLAGS: -fsanitize=alignment,undefined - PG_TEST_INITDB_EXTRA_OPTS: >- - -c io_method=io_uring - - configure_script: | - su postgres <<-EOF - set -e - meson setup \ - ${MESON_COMMON_PG_CONFIG_ARGS} \ - --buildtype=debug \ - ${LINUX_MESON_FEATURES} -Dllvm=enabled \ - build - EOF - - # Also build & test in a 32bit build - it's gotten rare to test that - # locally. - configure_32_script: | - su postgres <<-EOF - set -e - export CC='ccache gcc -m32' - export CXX='ccache g++ -m32' - meson setup \ - ${MESON_COMMON_PG_CONFIG_ARGS} \ - --buildtype=debug \ - --pkg-config-path /usr/lib/i386-linux-gnu/pkgconfig/ \ - -DPERL=perl5.40-i386-linux-gnu \ - ${LINUX_MESON_FEATURES} -Dlibnuma=disabled \ - build-32 - EOF - - build_script: | - su postgres <<-EOF - set -e - ninja -C build -j${BUILD_JOBS} ${MBUILD_TARGET} - ninja -C build -t missingdeps - EOF - - build_32_script: | - su postgres <<-EOF - set -e - ninja -C build-32 -j${BUILD_JOBS} ${MBUILD_TARGET} - ninja -C build -t missingdeps - EOF - - upload_caches: ccache - - test_world_script: | - su postgres <<-EOF - set -e - ulimit -c unlimited - meson test $MTEST_ARGS --num-processes ${TEST_JOBS} - EOF - # so that we don't upload 64bit logs if 32bit fails - rm -rf build/ - - # There's currently no coverage of icu with LANG=C in the buildfarm. We - # can easily provide some here by running one of the sets of tests that - # way. Newer versions of python insist on changing the LC_CTYPE away - # from C, prevent that with PYTHONCOERCECLOCALE. - test_world_32_script: | - su postgres <<-EOF - set -e - ulimit -c unlimited - PYTHONCOERCECLOCALE=0 LANG=C meson test $MTEST_ARGS -C build-32 --num-processes ${TEST_JOBS} - EOF - - on_failure: - <<: *on_failure_meson - - on_failure: - cores_script: src/tools/ci/cores_backtrace.sh linux /tmp/cores - - -# NB: macOS is by far the most expensive OS to run CI for, therefore no -# expensive additional checks should be added. -# -# SPECIAL: -# - Enables --clone for pg_upgrade and pg_combinebackup -task: - name: macOS - Sequoia - Meson - - env: - CPUS: 4 # always get that much for cirrusci macOS instances - BUILD_JOBS: $CPUS - # Test performance regresses noticeably when using all cores. 8 seems to - # work OK. See - # https://postgr.es/m/20220927040208.l3shfcidovpzqxfh%40awork3.anarazel.de - TEST_JOBS: 8 - IMAGE: ghcr.io/cirruslabs/macos-runner:sequoia - - CIRRUS_WORKING_DIR: ${HOME}/pgsql/ - CCACHE_DIR: ${HOME}/ccache - MACPORTS_CACHE: ${HOME}/macports-cache - - MESON_FEATURES: >- - -Dbonjour=enabled - -Ddtrace=enabled - -Dgssapi=enabled - -Dlibcurl=enabled - -Dnls=enabled - -Duuid=e2fs - - MACOS_PACKAGE_LIST: >- - ccache - icu - kerberos5 - lz4 - meson - openldap - openssl - p5.34-io-tty - p5.34-ipc-run - python312 - tcl - zstd - - CC: ccache cc - CXX: ccache c++ - CFLAGS: -Og -ggdb - CXXFLAGS: -Og -ggdb - - PG_TEST_PG_UPGRADE_MODE: --clone - PG_TEST_PG_COMBINEBACKUP_MODE: --clone - - <<: *macos_task_template - - depends_on: SanityCheck - only_if: $CI_MACOS_ENABLED - - sysinfo_script: | - id - uname -a - ulimit -a -H && ulimit -a -S - export - - setup_core_files_script: - - mkdir ${HOME}/cores - - sudo sysctl kern.corefile="${HOME}/cores/core.%P" - - # Use macports, even though homebrew is installed. The installation - # of the additional packages we need would take quite a while with - # homebrew, even if we cache the downloads. We can't cache all of - # homebrew, because it's already large. So we use macports. To cache - # the installation we create a .dmg file that we mount if it already - # exists. - # XXX: The reason for the direct p5.34* references is that we'd need - # the large macport tree around to figure out that p5-io-tty is - # actually p5.34-io-tty. Using the unversioned name works, but - # updates macports every time. - macports_cache: - folder: ${MACPORTS_CACHE} - fingerprint_script: | - # Reinstall packages if the OS major version, the list of the packages - # to install or the MacPorts install script changes. - sw_vers -productVersion | sed 's/\..*//' - echo $MACOS_PACKAGE_LIST - md5 src/tools/ci/ci_macports_packages.sh - reupload_on_changes: true - setup_additional_packages_script: | - sh src/tools/ci/ci_macports_packages.sh $MACOS_PACKAGE_LIST - # system python doesn't provide headers - sudo /opt/local/bin/port select python3 python312 - # Make macports install visible for subsequent steps - echo PATH=/opt/local/sbin/:/opt/local/bin/:$PATH >> $CIRRUS_ENV - upload_caches: macports - - ccache_cache: - folder: $CCACHE_DIR - configure_script: | - export PKG_CONFIG_PATH="/opt/local/lib/pkgconfig/" - meson setup \ - ${MESON_COMMON_PG_CONFIG_ARGS} \ - --buildtype=debug \ - -Dextra_include_dirs=/opt/local/include \ - -Dextra_lib_dirs=/opt/local/lib \ - ${MESON_COMMON_FEATURES} ${MESON_FEATURES} \ - build - - build_script: ninja -C build -j${BUILD_JOBS} ${MBUILD_TARGET} - upload_caches: ccache - - test_world_script: | - ulimit -c unlimited # default is 0 - ulimit -n 1024 # default is 256, pretty low - meson test $MTEST_ARGS --num-processes ${TEST_JOBS} - - on_failure: - <<: *on_failure_meson - cores_script: src/tools/ci/cores_backtrace.sh macos "${HOME}/cores" - - -WINDOWS_ENVIRONMENT_BASE: &WINDOWS_ENVIRONMENT_BASE - env: - # Half the allowed per-user CPU cores - CPUS: 4 - - # The default cirrus working dir is in a directory msbuild complains about - CIRRUS_WORKING_DIR: "c:/cirrus" - # git's tar doesn't deal with drive letters, see - # https://postgr.es/m/b6782dc3-a7b0-ed56-175f-f8f54cb08d67%40dunslane.net - TAR: "c:/windows/system32/tar.exe" - # Avoids port conflicts between concurrent tap test runs - PG_TEST_USE_UNIX_SOCKETS: 1 - PG_REGRESS_SOCK_DIR: "c:/cirrus/" - DISK_SIZE: 50 - IMAGE_FAMILY: pg-ci-windows-ci - - sysinfo_script: | - chcp - systeminfo - powershell -Command get-psdrive -psprovider filesystem - set - - -task: - name: Windows - Server 2022, VS 2019 - Meson & ninja - << : *WINDOWS_ENVIRONMENT_BASE - - env: - TEST_JOBS: 8 # wild guess, data based value welcome - - # Cirrus defaults to SetErrorMode(SEM_NOGPFAULTERRORBOX | ...). That - # prevents crash reporting from working unless binaries do SetErrorMode() - # themselves. Furthermore, it appears that either python or, more likely, - # the C runtime has a bug where SEM_NOGPFAULTERRORBOX can very - # occasionally *trigger* a crash on process exit - which is hard to debug, - # given that it explicitly prevents crash dumps from working... - # 0x8001 is SEM_FAILCRITICALERRORS | SEM_NOOPENFILEERRORBOX - CIRRUS_WINDOWS_ERROR_MODE: 0x8001 - - MESON_FEATURES: - -Dcpp_args=/std:c++20 - -Dauto_features=disabled - -Dldap=enabled - -Dssl=openssl - -Dtap_tests=enabled - -Dplperl=enabled - -Dplpython=enabled - - <<: *windows_task_template - - depends_on: SanityCheck - only_if: $CI_WINDOWS_ENABLED - - setup_additional_packages_script: | - REM choco install -y --no-progress ... - - setup_hosts_file_script: | - echo 127.0.0.1 pg-loadbalancetest >> c:\Windows\System32\Drivers\etc\hosts - echo 127.0.0.2 pg-loadbalancetest >> c:\Windows\System32\Drivers\etc\hosts - echo 127.0.0.3 pg-loadbalancetest >> c:\Windows\System32\Drivers\etc\hosts - type c:\Windows\System32\Drivers\etc\hosts - - configure_script: | - vcvarsall x64 - meson setup --backend ninja %MESON_COMMON_PG_CONFIG_ARGS% --buildtype debug -Db_pch=true -Dextra_lib_dirs=c:\openssl\1.1\lib -Dextra_include_dirs=c:\openssl\1.1\include -DTAR=%TAR% %MESON_FEATURES% build - - build_script: | - vcvarsall x64 - ninja -C build %MBUILD_TARGET% - ninja -C build -t missingdeps - - check_world_script: | - vcvarsall x64 - meson test %MTEST_ARGS% --num-processes %TEST_JOBS% - - on_failure: - <<: *on_failure_meson - crashlog_artifacts: - path: "crashlog-*.txt" - type: text/plain - - -task: - << : *WINDOWS_ENVIRONMENT_BASE - name: Windows - Server 2022, MinGW64 - Meson - - # See REPO_CI_AUTOMATIC_TRIGGER_TASKS in .cirrus.star. - trigger_type: $CI_TRIGGER_TYPE_MINGW - - depends_on: SanityCheck - only_if: $CI_MINGW_ENABLED - - env: - TEST_JOBS: 4 # higher concurrency causes occasional failures - CCACHE_DIR: C:/msys64/ccache - CCACHE_MAXSIZE: "500M" - CCACHE_SLOPPINESS: pch_defines,time_macros - CCACHE_DEPEND: 1 - # for some reason mingw plpython cannot find its installation without this - PYTHONHOME: C:/msys64/ucrt64 - # prevents MSYS bash from resetting error mode - MSYS: winjitdebug - # Start bash in current working directory - CHERE_INVOKING: 1 - BASH: C:\msys64\usr\bin\bash.exe -l - - # Keep -Dnls explicitly disabled, as the number of files it creates causes a - # noticeable slowdown. - MESON_FEATURES: >- - -Dnls=disabled - - <<: *windows_task_template - - ccache_cache: - folder: ${CCACHE_DIR} - - setup_additional_packages_script: | - REM C:\msys64\usr\bin\pacman.exe -S --noconfirm ... - - mingw_info_script: | - %BASH% -c "where gcc" - %BASH% -c "gcc --version" - %BASH% -c "where perl" - %BASH% -c "perl --version" - - configure_script: | - %BASH% -c "meson setup %MESON_COMMON_PG_CONFIG_ARGS% -Ddebug=true -Doptimization=g -Db_pch=true %MESON_COMMON_FEATURES% %MESON_FEATURES% -DTAR=%TAR% build" - - build_script: | - %BASH% -c "ninja -C build ${MBUILD_TARGET}" - - upload_caches: ccache - - test_world_script: | - %BASH% -c "meson test %MTEST_ARGS% --num-processes %TEST_JOBS%" - - on_failure: - <<: *on_failure_meson - crashlog_artifacts: - path: "crashlog-*.txt" - type: text/plain - - -task: - name: CompilerWarnings - - # To limit unnecessary work only run this once the SanityCheck - # succeeds. This is particularly important for this task as we intentionally - # use always: to continue after failures. - depends_on: SanityCheck - only_if: $CI_COMPILERWARNINGS_ENABLED - - env: - CPUS: 4 - BUILD_JOBS: 4 - IMAGE_FAMILY: pg-ci-trixie - - # Use larger ccache cache, as this task compiles with multiple compilers / - # flag combinations - CCACHE_MAXSIZE: "1G" - CCACHE_DIR: "/tmp/ccache_dir" - - LINUX_CONFIGURE_FEATURES: *LINUX_CONFIGURE_FEATURES - - <<: *linux_task_template - - sysinfo_script: | - id - uname -a - cat /proc/cmdline - ulimit -a -H && ulimit -a -S - gcc -v - clang -v - export - - ccache_cache: - folder: $CCACHE_DIR - - setup_additional_packages_script: | - #apt-get update - #DEBIAN_FRONTEND=noninteractive apt-get -y install ... - - ### - # Test that code can be built with gcc/clang without warnings - ### - - setup_script: echo "COPT=-Werror" > src/Makefile.custom - - # Trace probes have a history of getting accidentally broken. Use the - # different compilers to build with different combinations of dtrace on/off - # and cassert on/off. - - # gcc, cassert off, dtrace on - always: - gcc_warning_script: | - time ./configure \ - --cache gcc.cache \ - --enable-dtrace \ - ${LINUX_CONFIGURE_FEATURES} \ - CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang" - make -s -j${BUILD_JOBS} clean - time make -s -j${BUILD_JOBS} world-bin - - # gcc, cassert on, dtrace off - always: - gcc_a_warning_script: | - time ./configure \ - --cache gcc.cache \ - --enable-cassert \ - ${LINUX_CONFIGURE_FEATURES} \ - CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang" - make -s -j${BUILD_JOBS} clean - time make -s -j${BUILD_JOBS} world-bin - - # clang, cassert off, dtrace off - always: - clang_warning_script: | - time ./configure \ - --cache clang.cache \ - ${LINUX_CONFIGURE_FEATURES} \ - CC="ccache clang" CXX="ccache clang++" CLANG="ccache clang" - make -s -j${BUILD_JOBS} clean - time make -s -j${BUILD_JOBS} world-bin - - # clang, cassert on, dtrace on - always: - clang_a_warning_script: | - time ./configure \ - --cache clang.cache \ - --enable-cassert \ - --enable-dtrace \ - ${LINUX_CONFIGURE_FEATURES} \ - CC="ccache clang" CXX="ccache clang++" CLANG="ccache clang" - make -s -j${BUILD_JOBS} clean - time make -s -j${BUILD_JOBS} world-bin - - # cross-compile to windows - always: - mingw_cross_warning_script: | - time ./configure \ - --host=x86_64-w64-mingw32ucrt \ - --enable-cassert \ - --without-icu \ - CC="ccache x86_64-w64-mingw32ucrt-gcc" \ - CXX="ccache x86_64-w64-mingw32ucrt-g++" - make -s -j${BUILD_JOBS} clean - time make -s -j${BUILD_JOBS} world-bin - - ### - # Verify docs can be built - ### - # XXX: Only do this if there have been changes in doc/ since last build - always: - docs_build_script: | - time ./configure \ - --cache gcc.cache \ - CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang" - make -s -j${BUILD_JOBS} clean - time make -s -j${BUILD_JOBS} -C doc - - ### - # Verify headerscheck / cpluspluscheck succeed - # - # - Run both in same script to increase parallelism, use -k to get result of both - # - Use -fmax-errors, as particularly cpluspluscheck can be very verbose - ### - always: - headers_headerscheck_script: | - time ./configure \ - ${LINUX_CONFIGURE_FEATURES} \ - --cache gcc.cache \ - --quiet \ - CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang" - make -s -j${BUILD_JOBS} clean - time make -s -j${BUILD_JOBS} -k ${CHECKFLAGS} headerscheck cpluspluscheck EXTRAFLAGS='-fmax-errors=10' - - always: - upload_caches: ccache diff --git a/src/tools/ci/ci_macports_packages.sh b/src/tools/ci/ci_macports_packages.sh index e49f4f703a0..092d8cd7e8f 100755 --- a/src/tools/ci/ci_macports_packages.sh +++ b/src/tools/ci/ci_macports_packages.sh @@ -6,8 +6,7 @@ # when packages are installed or removed. Any package this script is # not instructed to install, will be removed again. # -# This currently expects to be run in a GitHub Actions or cirrus-ci -# macOS environment. +# This currently expects to be run in a GitHub Actions macOS environment. set -e # set -x @@ -39,8 +38,8 @@ fi cache_dmg="macports.hfs.dmg" -if [ "$CIRRUS_CI" != "true" ] && [ "$GITHUB_ACTIONS" != "true" ]; then - echo "expect to be called within cirrus-ci or GitHub Actions" 1>&2 +if [ "$GITHUB_ACTIONS" != "true" ]; then + echo "expect to be called within GitHub Actions" 1>&2 exit 1 fi diff --git a/src/tools/ci/gcp_ram_disk.sh b/src/tools/ci/gcp_ram_disk.sh deleted file mode 100755 index 18dbb2037f5..00000000000 --- a/src/tools/ci/gcp_ram_disk.sh +++ /dev/null @@ -1,27 +0,0 @@ -#!/bin/sh -# Move working directory into a RAM disk for better performance. - -set -e -set -x - -mv $CIRRUS_WORKING_DIR $CIRRUS_WORKING_DIR.orig -mkdir $CIRRUS_WORKING_DIR - -case "`uname`" in - FreeBSD|NetBSD) - mount -t tmpfs tmpfs $CIRRUS_WORKING_DIR - ;; - OpenBSD) - umount /dev/sd0j # unused /usr/obj partition - printf "m j\n\n\nswap\nw\nq\n" | disklabel -E sd0 - swapon /dev/sd0j - # Remove the per-process data segment limit so that mount_mfs can allocate - # large memory filesystems. Without this, mount_mfs mmap() may fail with - # "Cannot allocate memory" if the requested size exceeds the current - # datasize limit. - ulimit -d unlimited - mount -t mfs -o rw,noatime,nodev,-s=10000000 swap $CIRRUS_WORKING_DIR - ;; -esac - -cp -a $CIRRUS_WORKING_DIR.orig/. $CIRRUS_WORKING_DIR/ -- 2.54.0.380.gc69baaf57b --vdbxiaou22xpj6rk-- ^ permalink raw reply [nested|flat] 309+ messages in thread
end of thread, other threads:[~2026-06-04 13:34 UTC | newest] Thread overview: 309+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]> 2026-06-04 13:34 [PATCH v11a 2/2] ci: Remove support for cirrus-ci based CI Andres Freund <[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